Sameer Tilak, Ph.D. - US grants

National Science Foundation
NSF Software Development for Cyberinfrastructure (SDCI) Program
Office of Cyberinfrastructure

Proposal Number: 0722067
Principal Investigator: Tony Fountain
Institution: University of California-San Diego
Proposal Title: SDCI NMI Improvement: The Ring Buffer Network Bus (RBNB) DataTurbine Streaming Data System

Abstract

This project will transition the commercial system DataTurbine into an open source software system, while specifically enhancing the middleware across a number of areas. DataLogger supports reliable data transport and the integration of sensors and remote instruments into Cyberinfrastructure through a set of services supporting data streaming and management. Work areas include visualization, single sign-on, adding datalogger drivers, benchmarking, porting to 64-bit architectures, and other enhancements. Intellectual merit lies in the realization of bringing sensors into the CI continuum and insights gained in applying this technology to observing systems. Broad impact includes direct operational integration for a number of NSF observing systems, including NEON, NEES, and CUAHSI.

The University of Michigan Ann Arbor is awarded a grant to support a two-day workshop focused on planning, deployment and operation of advanced aquatic sensors. The workshop will be conducted by the Global Lakes Ecological Observatory Network (GLEON) and the Great Lakes Partner of the Alliance for Coastal Technologies (ACT), and will be hosted by the University of Michigan Biological Station (UMBS). Aquatic sensor technology is developing rapidly, yet mechanisms and opportunities for limnologists and field biologists to receive exposure to and training in these new technologies are limited. The workshop will address several critical aspects of data collection and management, as well as instrument lifecycle, which are routinely encountered by users of aquatic sensors. These topics include: exchange of knowledge among leading aquatic sensor developers and the end-users of this technology; assembly of project teams for the purpose of deploying, operating and maintaining sensor networks; demonstration of the latest in aquatic sensor and sensor platform technology; development of sensor-oriented curriculum for limnologists and field biologists; fundamental skills needed for sensor deployments such as data logger configuration, data telemetry and data management. Products of the workshop will include a report on the technologies demonstrated and multimedia(recorded audio visuals) from panels and presentations will be made freely available online.

The workshop will, for the first time, bring together members of the Alliance for Coastal Technologies (http://act-us.info) and the Global Lake Ecological Observatory Network (http://www.gleon.org). The complementary missions of these organizations, sensor evaluation (ACT) and sensor applications (GLEON), affords opportunities for discussions on future collaborations. The workshop will also provide opportunities for graduate students and young researchers from diverse regions and backgrounds, including students and researchers working for upper Midwestern Native American tribal organizations, to gain skills in acquiring and applying data derived from state-of-the-science aquatic sensors. It will also provide students and young investigators with opportunities to collaborate across disciplinary and geographic boundaries.

This project will catalyze a new generation of sensor-based streaming data applications by building on the foundation of the Open Source DataTurbine (OSDT) middleware (www.dataturbine.org). This will involve strategic software development, systems integration and testing, science experiments, and education and outreach. The software developments will include (A) tools for configuring, testing, and controlling distributed sensor systems, (B) software interfaces that are compliant with the Open Geospatial Consortium Sensor Web Enablement standards, (C) a new OSDT-Matlab interface, and (D) OSDT cybersecurity enhancements. These software products will be integrated into the production research infrastructures at Purdue, the University of Connecticut, the North Temperate Lake LTER Network site, and the Monterey Bay Aquarium Research Institute. The software will be professionally developed and managed as community resources. The intellectual merit of this project will be advances in software engineering, interoperability standards, and systems management for complex real-time sensor systems as well as advances on important open questions in civil engineering, marine science, and ecology. This project will yield broader impacts by enabling new science applications, enhancing productivity, and accelerating innovation across NSF directorates. To ensure that these broader impacts are realized, the team will provide student research opportunities, develop curriculum materials and training courses, and cultivate a community of software users.

This experimental activity focuses on configuring, maintaining, and adaptive power management of remote sensors and their embedded software used in environmental observing systems. The approach is based on a well known and popular cluster configuration system out of UCSD called Rocks. Sensor platforms and sensor networks require scalable and reliable solutions to manage their software configurations. This activity sets out to prove or disprove that a solution proven to work for heterogeneous cluster and data center configuration and management (ROCKS)can be applied to distributed sensors. Attached to this work is a set of integrated research and development activities on improved power management for sensor platforms and their operational workloads. Broader impact derives from the initial targeted communities in limnology and marine science with associated real world scenarios, and extends to other environmental observing systems as well as disaster response. Educational content from the work will be developed and inserted into a graduate level course at UCSD on embedded computing. Intellectual merit is found in the new approach to sensor reproducibility and adaptive power management algorithms.

Current healthcare diagnostics and assessment systems are limited by health data, which is sporadic, periodic, and incomplete. Wireless devices and health sensor technologies are increasing in use for continuous monitoring and assessment of key physiologic, psychological, and environmental variables and reduce the current gaps in health data. Uptake of such data by current health systems has been slow because of the reliance upon the physician/healthcare team to interpret and manage incoming data. Nevertheless, the large streams of data generated by these devices in conjunction with traditional clinical data (Electronic Medical Records) have the potential provide real and important insights into patient health and behavior. To address this gap, this proposal will develop SenseHealth -- a novel software platform that will automatically process and incorporate volumes of real-time data from sensors tailored to the individual in the context of personal electronic medical records and available environmental data. Such data will be integrated into the clinical care workflow to enable system usability, feasibility, and ultimately utility. A core component of the cyberinfrastructure is a collection of quantitative, predictive models that are sensitive to concerns across age, diseases, and health and variety of patient situations (ranging from low priority with no consequence on patient management to high priority requiring emergency evaluation), and sensor failures. The models will be integrated with a distributed real-time stream data processing system and a complex event stream processing engine to process sensor data in a scalable and fault-tolerant manner. Research at Rady Children's Hospital of San Diego, an affiliate of UCSD will be leveraged to develop these models. In each of the following studies, clinically relevant events (i.e. events that require clinical intervention) will be identified and disease specific models will be developed that will predict clinical relevance or the need for intervention. Incoming data and resulting clinical management activity from studies using various types of health sensors will be evaluated in two different patient populations: (1) MyGlucoHealth application for evaluating the use of a Bluetooth-enabled glucometer (for blood sugar measurements) in 40 youths with Type 1 diabetes, and (2) Asthma Tracking application for evaluating the ability of a metered dose inhaler (MDI) tracking device to track asthma medication use in 50 mild-to-moderate asthma subjects over a period of 6 months. The models will then be evaluated using multiple sensor streams in youth with diabetes (The Diabetes Management Integrated Technology Research Initiative (DMITRI) study) and in a prospective study in youth with asthma to determine their validity, efficacy, and utility in identifying patient scenarios of concern.

The SenseHealth system architecture will consist of four major components (1) Health and environmental sensors linked with (2) smartphone applications that communicate with (3) a back-end Data Center comprised of data storage and clusters doing and real-time analytics and data visualization, which will then provide a comprehensive health picture to users/clients via (4) tailored, programmed user/client applications. For these continuous sensing applications, managing sensors and smartphone in an energy-efficient manner is critical. SenseHealth will include a novel context-aware power management framework that uses both the application-level context (e.g., sensor data) and the dynamic environmental or system-level context (e.g., battery level, next phone charging opportunity prediction, or bandwidth availability) to adaptively control the state of hardware components and deliver a consistent performance (e.g. data accuracy, latency). In particular, data sampling protocols will be energy-aware and will be designed to sample data accurately but only as necessary to provide relevant clinical information. SenseHealth will use Storm, an open source distributed real-time computation system to process the data in a scalable and fault-tolerant manner. The aforementioned predictive models will be implemented in ESPER, an open-source complex event processing (CEP) engine. The models will use ESPER's rich Event Processing Language (EPL) to express filtering, aggregation, and joins, possibly over sliding windows of multiple event streams and pattern semantics to express complex temporal causality among events and trigger custom actions when event conditions occur among event streams. Finally, SenseHealth will fuse sensor and clinical data in a visual format that will increase interpretability and comprehension independent of literacy levels and will provide feedback and ultimately intervention support that is timely and relevant to the user (patient and clinician) based on comprehensive knowledge of data. Open source software visualization tools developed at Calit2 that leverage advances in scaled display wall technology will serve as the foundation for the data visualization component. NSF-funded DELPHI project will provide the data center component to store health sensor data and provide access to SenseHealth algorithm-processed data and visualization protocols.

The research itself will have direct impact on two patient communities, but the broader impacts of the proposed research will extend well beyond them. The proposed open software platform will be built with flexibility to allow for alternative programming with plug-and-play data processing algorithms as required for various sensors/data sources/clinical scenarios. The results from the proposed development activities and prototyping experiments will be of tremendous value to medical professionals, scientists and engineers who are engaged in planning and developing sensor-based systems for continuous health monitoring. The developed software products will be publicly available as open source products under the Apache license. The tools developed from this proposal will be designed to be extensible so that other sensors as well as models can easily be integrated and impact a broader range of healthcare applications. SenseHealth is an essential step toward providing a real-time 360-degree snapshot of health to optimize patient-centered, evidence-based decisions and to empower patients to participate in their own healthcare. The project team will contribute to training a diverse next generation of scientists by involving undergraduate students in the development process, both for computer science techniques and medical science research. The exciting aspect of this proposed work is that wellness is a very tangible and important factor even at young age. The education program will be structured to excite students, particularly those from traditionally underrepresented groups such as minorities and females, about multi-disciplinary research. Through the UCSD's COSMOS program, simple, fun and hands-on experiences for these students will be designed to allow them to understand importance of self-health assessment and disease management at an early age. The team is involved heavily in Graduate Medical Education at UCSD and will promote use of SenseHealth to integrate health data into current health systems in fellowship training activities. This proposal also funds for one graduate student.

A science gateway is a community-developed set of tools, applications, and data collections that are integrated via a portal or a suite of applications. It provides easy, typically browser-based, access to supercomputers, software tools, and data repositories to allow researchers to focus on their scientific goals and less on the cyberinfrastructure. These gateways are fostering collaboration and exchange of ideas among thousands of researchers from multiple communities ranging from atmospheric science, astrophysics, chemistry, biophysics, biochemistry, earthquake engineering, geophysics, to neuroscience, and biology. However due to limited development and administrative personnel resources, science gateways often leverage only a small subset of the NSF-funded CI to mitigate the complexities involved with using multiple resource and services at scale in part due to software and hardware failures. Since many successful science gateways have had unprecedented growth in their user base and ever increasing datasets, increasing their usage of CI resources without introducing additional complexity would help them meet this demand.

In response to this need, an Automated Monitoring AnalySis Service (AMASS) will be built to provide a flexible and extensible service for automated analysis of monitoring data initially focused on science gateways. AMASS will be based on data mining and machine learning techniques and emerging big data technologies to analyze monitoring data for improving the reliability and operational efficiency of CI as well as progress on fundamental questions in systematic and population biology, computational neuroscience, and biophysics communities. Along with AMASS, a simulation framework will be built for testing automated analysis algorithms and adaptive execution techniques. An intuitive query API will be provided for science gateway software to use and will be integrated into the following three target science gateways that will drive the project's research and development: the Cyberinfrastructure for Phylogenetic Research (CIPRES), the Neuroscience Gateway (NSG), and UltraScan. The proposed approach does not require any changes to the end user applications, and the software developments will significantly enhance the science productivity and user satisfaction of science gateways by integrating monitoring data into their infrastructure to enable adaptive execution of their applications, allowing scientists to answer more sophisticated questions without having to understand the complexities of a large-scale distributed environment. The developed software products will be available as open source products under an Apache License and will be integrated into the NSF-funded SciGap project in order to impact a broader range of science gateways.